Parameter Selection Algorithm for Support Vector Machine

AbstractSupport Vector Machine (SVM) is a new modeling method. It has shown good performance in many field and mostly outperformed neural networks. The parameter selection should to be done before training SVM. Modified particle swarm optimization (POS) was adpoted to select parameters of SVM. It is shown by simulation that the modified POS algorithm can derive a set of optimal parameters of SVM. Compared with neural networks, SVM model possess some advantages such as simple structure, fast convergence speed with high generalization ability